© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26474
    Prev
    Next
    INDEX
    Explanations

    patterns in structured data or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    432
    +0.13
    0.7%
    156
    +0.12
    0.7%
    364
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    432
    +0.13
    0.02
    102
    +0.12
    0.01
    164
    +0.11
    0.02
    Negative Logits
    ipal
    -1.84
    ourier
    -1.62
     vice
    -1.32
    agers
    -1.31
     consequence
    -1.31
    ³³
    -1.30
     duo
    -1.28
    PLC
    -1.27
    tig
    -1.26
    pex
    -1.24
    POSITIVE LOGITS
    lessly
    1.72
    !"
    1.64
    !");
    1.62
    mos
    1.53
    .]
    1.50
    !
    1.49
    "}](#
    1.49
     itself
    1.42
    fully
    1.41
    ToString
    1.40
    Activations Density 0.178%

    No Known Activations